Learning with Feature-Dependent Label Noise: A Progressive ApproachDownload PDF

Sep 28, 2020 (edited Mar 27, 2021)ICLR 2021 SpotlightReaders: Everyone
  • Keywords: Noisy Label, Deep Learning, Classification
  • Abstract: Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two categories: they either assume an ideal feature-independent noise, or remain heuristic without theoretical guarantees. In this paper, we propose to target a new family of feature-dependent label noise, which is much more general than commonly used i.i.d. label noise and encompasses a broad spectrum of noise patterns. Focusing on this general noise family, we propose a progressive label correction algorithm that iteratively corrects labels and refines the model. We provide theoretical guarantees showing that for a wide variety of (unknown) noise patterns, a classifier trained with this strategy converges to be consistent with the Bayes classifier. In experiments, our method outperforms SOTA baselines and is robust to various noise types and levels.
  • One-sentence Summary: We propose a progressive label correction approach for noisy label learning task.
  • Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
14 Replies

Loading